Multimodal learning with graphs

Y Ektefaie, G Dasoulas, A Noori, M Farhat… - Nature Machine …, 2023‏ - nature.com
Artificial intelligence for graphs has achieved remarkable success in modelling complex
systems, ranging from dynamic networks in biology to interacting particle systems in physics …

Robotic vision for human-robot interaction and collaboration: A survey and systematic review

N Robinson, B Tidd, D Campbell, D Kulić… - ACM Transactions on …, 2023‏ - dl.acm.org
Robotic vision, otherwise known as computer vision for robots, is a critical process for robots
to collect and interpret detailed information related to human actions, goals, and …

Gen-vlkt: Simplify association and enhance interaction understanding for hoi detection

Y Liao, A Zhang, M Lu, Y Wang… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
Abstract The task of Human-Object Interaction (HOI) detection could be divided into two core
problems, ie, human-object association and interaction understanding. In this paper, we …

Hoiclip: Efficient knowledge transfer for hoi detection with vision-language models

S Ning, L Qiu, Y Liu, X He - … of the IEEE/CVF conference on …, 2023‏ - openaccess.thecvf.com
Abstract Human-Object Interaction (HOI) detection aims to localize human-object pairs and
recognize their interactions. Recently, Contrastive Language-Image Pre-training (CLIP) has …

Viplo: Vision transformer based pose-conditioned self-loop graph for human-object interaction detection

J Park, JW Park, JS Lee - … of the IEEE/CVF conference on …, 2023‏ - openaccess.thecvf.com
Abstract Human-Object Interaction (HOI) detection, which localizes and infers relationships
between human and objects, plays an important role in scene understanding. Although two …

Relational context learning for human-object interaction detection

S Kim, D Jung, M Cho - … of the IEEE/CVF conference on …, 2023‏ - openaccess.thecvf.com
Recent state-of-the-art methods for HOI detection typically build on transformer architectures
with two decoder branches, one for human-object pair detection and the other for interaction …

Exploring predicate visual context in detecting of human-object interactions

FZ Zhang, Y Yuan, D Campbell… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Recently, the DETR framework has emerged as the dominant approach for human--object
interaction (HOI) research. In particular, two-stage transformer-based HOI detectors are …

Exploring structure-aware transformer over interaction proposals for human-object interaction detection

Y Zhang, Y Pan, T Yao, R Huang… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
Abstract Recent high-performing Human-Object Interaction (HOI) detection techniques have
been highly influenced by Transformer-based object detector (ie, DETR). Nevertheless, most …

Efficient two-stage detection of human-object interactions with a novel unary-pairwise transformer

FZ Zhang, D Campbell, S Gould - Proceedings of the IEEE …, 2022‏ - openaccess.thecvf.com
Recent developments in transformer models for visual data have led to significant
improvements in recognition and detection tasks. In particular, using learnable queries in …

Human-object interaction detection via disentangled transformer

D Zhou, Z Liu, J Wang, L Wang, T Hu… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
Abstract Human-Object Interaction Detection tackles the problem of joint localization and
classification of human object interactions. Existing HOI transformers either adopt a single …